Borrowing it
Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/audit/SKILL.mdgit clone --depth 1 https://github.com/senda-labs/DQIII8Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/senda-labs/dqiii8/audit)<a href="https://agentmods.dev/skills/senda-labs/dqiii8/audit"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/audit"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00691 |
| Opus 5 | $0.00018 | $0.00345 |
| Sonnet 5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit -- System Health Audit
Triggers the auditor agent to analyze database/dqiii8.db and produce a structured health report.
Usage
/audit
/audit --period 30d # analyze last 30 days instead of default 7
/audit --agent python-specialist # scope to one agent
Scope note — sessions / morning_report / loop_effectiveness
.claude/hooks/stop.py:439 writes sessions from every CLI session
(INSERT ... ON CONFLICT(session_id) DO UPDATE), gated on
_total_actions > 0 (stop.py:436). So sessions is only populated when
agent_actions has ≥1 row for that session, which makes a near-empty
sessions table a second, independent detector for an agent_actions
outage — a real signal to chase, not noise to dismiss. Only morning_report
is genuinely bot-only (written solely by bin/ui/dqiii8_bot.py).
loop_effectiveness is a VIEW over objectives, which has 0 rows because the
autonomous-loop execution flow (bin/director.py loop mode) isn't in active
use yet — an empty result there is still expected, not a symptom to chase.
What it does
- Queries all metric tables:
agent_actions,error_log,sessions,skill_metrics - Uses views
agent_performanceanderror_keywords_freq - Computes an overall health score (0-100)
- Writes a Markdown report to
database/audit_reports/audit-YYYY-MM-DD-HH.md - Inserts a summary row in the
audit_reportstable - Prints a one-line summary to the terminal
Output
[AUDIT] Score: 87/100 | Actions: 106 | Success: 100.0% | Failures: 0 | Unresolved errors: 0
Report: database/audit_reports/audit-2026-03-11-14.md
Score interpretation
| Score | Status | Cadencia recomendada |
|---|---|---|
| >= 85 | HEALTHY | next audit in 7 days |
| 70-85 | WARNING | next audit in 3 days |
| < 70 | CRITICAL | next audit in 1 day, notify user |
Auto-trigger
The stop.py hook automatically triggers /audit when 7+ days have passed since the last report in audit_reports. Also auto-invoked when errors accumulate during a session.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 70 lines · 36 tokens per session scan A 595b07472235
audit is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 22d ago), licensed MIT. It adds 36 tokens to every session and 691 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
using-adaptive-harness
Auto-mode bootstrap for adaptive-harness. Intercepts tasks, routes to optimal harness, evaluates results. Use on every task when adaptive-harness auto-mode is active.
task-taxonomy
Reference for the 6-axis task taxonomy used by adaptive-harness routing. Use when user asks how tasks are classified.
harness-registry
Manage the adaptive-harness pool: list, inspect, promote, demote harnesses. Use when user asks about harness status or wants to manage the pool.
skill-review-response
Use when a reviewer, CI bot, or another AI leaves feedback to address.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
video-maker
A workflow for designing, coding, rendering, and checking videos with Remotion or HyperFrames. Remotion uses React and TypeScript components, while HyperFrames uses HTML, CSS, and GSAP scenes.